{"id":34,"date":"2026-05-06T09:30:09","date_gmt":"2026-05-06T09:30:09","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/?page_id=34"},"modified":"2026-05-06T14:18:41","modified_gmt":"2026-05-06T14:18:41","slug":"project2","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/","title":{"rendered":"Project 2"},"content":{"rendered":"<section>\n  <h2>Cooperative Foundation Models for Object Detection Active Learning<\/h2>\n\n  <nav>\n    <strong>Introduction<\/strong> |\n    <a href=\"\/2026teamf11\/project2\/related-work\/\">Related Work<\/a> |\n    <a href=\"\/2026teamf11\/project2\/method\/\">Method<\/a> |\n    <a href=\"\/2026teamf11\/project2\/experiments\/\">Experiments<\/a> |\n    <a href=\"\/2026teamf11\/project2\/resources\/\">Resources<\/a> |\n    <a href=\"\/2026teamf11\/project2\/team\/\">Team<\/a>\n  <\/nav>\n\n  <hr>\n\n  <section>\n    <h2>Introduction<\/h2>\n\n    <h3>Problem Background<\/h3>\n\n    <p>\n      Object detection is a core computer vision task that requires a model to both recognize objects\n      and localize them with bounding boxes. It is widely used in applications such as autonomous\n      driving, remote sensing, surveillance, robotics, and industrial inspection.\n    <\/p>\n\n    <p>\n      However, training strong object detectors usually depends on large-scale bounding-box\n      annotations. Unlike image classification, where each image may only need one label, object\n      detection requires annotators to draw precise boxes around every object instance.\n    <\/p>\n\n<\/section>\n<\/section>\n    \n\n\n\n<section>\n<section>\n\n    <h3>Annotation Bottleneck<\/h3>\n\n    <p>\n      Bounding-box annotation is expensive and time-consuming. The cost grows quickly when the\n      dataset is large, when images contain many objects, or when the target domain requires\n      specialized knowledge.\n    <\/p>\n\n    <p>\n      Active learning helps reduce this cost by selecting only a subset of informative images for\n      annotation. However, even after active learning selects fewer images, humans still need to draw\n      bounding boxes from scratch on the selected samples.\n    <\/p>\n\n\n  <\/section>\n<\/section>\n\n\n<figure class=\"wp-block-image aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"412\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg\" alt=\"\" class=\"wp-image-143\" style=\"width:600px\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation-300x121.jpg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation-768x309.jpg 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n<section>\n<section>\n<h3>Limitations of Current Active Learning Pipelines<\/h3>\n\n    <p>\n      Existing active learning methods for object detection mainly focus on selecting which images\n      should be labeled. Many of them rely on detector confidence scores or diversity-based criteria,\n      but these signals do not fully capture the errors that matter most for detection.\n    <\/p>\n\n    <p>\n      In practice, detector confidence scores may be poorly calibrated, negative images are often\n      underused, and high-confidence false positives may be missed because the model appears\n      confident about them.\n    <\/p>\n\n\n    <h3>Project Goal<\/h3>\n\n    <p>\n      This project aims to make active learning for object detection more annotation-efficient. The\n      key question is how to reduce both the number of queried images and the effort required to\n      annotate each selected image.\n    <\/p>\n\n    <p>\n      To address this problem, we explore how multiple foundation models can assist different stages\n      of the active learning pipeline, while keeping humans in the loop for lightweight binary\n      verification instead of full manual box drawing.\n    <\/p>\n\n  <\/section>\n<\/section>\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Cooperative Foundation Models for Object Detection Active Learning Introduction | Related Work | Method | Experiments | Resources | Team Introduction Problem Background Object detection is a core computer vision task that requires a model to both recognize objects and localize them with bounding boxes. It is widely used in applications such as autonomous driving, [&hellip;]<\/p>\n","protected":false},"author":288,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-34","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\" \/>\n<meta property=\"og:description\" content=\"Cooperative Foundation Models for Object Detection Active Learning Introduction | Related Work | Method | Experiments | Resources | Team Introduction Problem Background Object detection is a core computer vision task that requires a model to both recognize objects and localize them with bounding boxes. It is widely used in applications such as autonomous driving, [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/\" \/>\n<meta property=\"og:site_name\" content=\"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-06T14:18:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"412\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/\",\"name\":\"Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/wp-content\\\/uploads\\\/sites\\\/153\\\/2026\\\/05\\\/motivation.jpg\",\"datePublished\":\"2026-05-06T09:30:09+00:00\",\"dateModified\":\"2026-05-06T14:18:41+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/wp-content\\\/uploads\\\/sites\\\/153\\\/2026\\\/05\\\/motivation.jpg\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/wp-content\\\/uploads\\\/sites\\\/153\\\/2026\\\/05\\\/motivation.jpg\",\"width\":1024,\"height\":412},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/project2\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Project 2\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\",\"name\":\"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/","og_locale":"en_US","og_type":"article","og_title":"Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","og_description":"Cooperative Foundation Models for Object Detection Active Learning Introduction | Related Work | Method | Experiments | Resources | Team Introduction Problem Background Object detection is a core computer vision task that requires a model to both recognize objects and localize them with bounding boxes. It is widely used in applications such as autonomous driving, [&hellip;]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/","og_site_name":"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","article_modified_time":"2026-05-06T14:18:41+00:00","og_image":[{"width":1024,"height":412,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/","name":"Project 2 - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg","datePublished":"2026-05-06T09:30:09+00:00","dateModified":"2026-05-06T14:18:41+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-content\/uploads\/sites\/153\/2026\/05\/motivation.jpg","width":1024,"height":412},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/project2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/"},{"@type":"ListItem","position":2,"name":"Project 2"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/","name":"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages\/34","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/users\/288"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/comments?post=34"}],"version-history":[{"count":22,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages\/34\/revisions"}],"predecessor-version":[{"id":150,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages\/34\/revisions\/150"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/media?parent=34"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}